BERT2D: Two Dimensional Positional Embeddings for Efficient Turkish NLP

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AJRLQM3B3" target="_blank" >RIV/00216208:11320/25:JRLQM3B3 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85194891514&doi=10.1109%2fACCESS.2024.3407983&partnerID=40&md5=e13a78472733dd2230be25d4fbf75df7" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85194891514&doi=10.1109%2fACCESS.2024.3407983&partnerID=40&md5=e13a78472733dd2230be25d4fbf75df7</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ACCESS.2024.3407983" target="_blank" >10.1109/ACCESS.2024.3407983</a>

Jazyk výsledku

angličtina

Název v původním jazyce

BERT2D: Two Dimensional Positional Embeddings for Efficient Turkish NLP

Popis výsledku v původním jazyce

This study addresses the challenge of improving the downstream performance of pretrained language models for morphologically rich languages, with a focus on Turkish. Traditional BERT models use one-dimensional absolute positional embeddings, which, while effective, have limitations when dealing with complex languages. We propose BERT2D, which is a novel BERT-based model that contributes to positional embedding systems. This approach introduces a dual embedding system that targets all the words and their subwords. Remarkably, this modification, coupled with whole word masking, resulted in a significant increase in performance despite a negligible increase in the parameters. Our experiments showed that BERT2D consistently outperformed the leading Turkish-focused BERT model, BERTurk, in terms of various performance metrics in text classification, token classification, and question-answering downstream tasks. For a fair comparison, we pretrained our BERT2D language model on the same dataset as that of BERTurk. The results demonstrate that two-dimensional positional embeddings can significantly improve the performance of encoder-only models in Turkish and other morphologically rich languages, suggesting a promising direction for future research in natural language processing. © 2013 IEEE.

Název v anglickém jazyce

BERT2D: Two Dimensional Positional Embeddings for Efficient Turkish NLP

Popis výsledku anglicky

This study addresses the challenge of improving the downstream performance of pretrained language models for morphologically rich languages, with a focus on Turkish. Traditional BERT models use one-dimensional absolute positional embeddings, which, while effective, have limitations when dealing with complex languages. We propose BERT2D, which is a novel BERT-based model that contributes to positional embedding systems. This approach introduces a dual embedding system that targets all the words and their subwords. Remarkably, this modification, coupled with whole word masking, resulted in a significant increase in performance despite a negligible increase in the parameters. Our experiments showed that BERT2D consistently outperformed the leading Turkish-focused BERT model, BERTurk, in terms of various performance metrics in text classification, token classification, and question-answering downstream tasks. For a fair comparison, we pretrained our BERT2D language model on the same dataset as that of BERTurk. The results demonstrate that two-dimensional positional embeddings can significantly improve the performance of encoder-only models in Turkish and other morphologically rich languages, suggesting a promising direction for future research in natural language processing. © 2013 IEEE.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE Access

ISSN

2169-3536

e-ISSN

—

Svazek periodika

12

Číslo periodika v rámci svazku

2024

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

13

Strana od-do

77429-77441

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85194891514